{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:5TDM332S2ZQLNMW6JYPLBLFJM6","short_pith_number":"pith:5TDM332S","canonical_record":{"source":{"id":"2607.26699","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-29T09:46:07Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"c090934a95cff9c2cd1c1d74c16edcd3d4ca528aea45a701e84ba2257d67d810","abstract_canon_sha256":"50723897969f12aa3f9e486197867976258b92d94e2027f1db08286f50b67f1b"},"schema_version":"1.0"},"canonical_sha256":"ecc6cdef52d660b6b2de4e1eb0aca967af3e0813ad5b3a444c789c1eac0671b2","source":{"kind":"arxiv","id":"2607.26699","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.26699","created_at":"2026-07-30T01:21:58Z"},{"alias_kind":"arxiv_version","alias_value":"2607.26699v1","created_at":"2026-07-30T01:21:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.26699","created_at":"2026-07-30T01:21:58Z"},{"alias_kind":"pith_short_12","alias_value":"5TDM332S2ZQL","created_at":"2026-07-30T01:21:58Z"},{"alias_kind":"pith_short_16","alias_value":"5TDM332S2ZQLNMW6","created_at":"2026-07-30T01:21:58Z"},{"alias_kind":"pith_short_8","alias_value":"5TDM332S","created_at":"2026-07-30T01:21:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:5TDM332S2ZQLNMW6JYPLBLFJM6","target":"record","payload":{"canonical_record":{"source":{"id":"2607.26699","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-29T09:46:07Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"c090934a95cff9c2cd1c1d74c16edcd3d4ca528aea45a701e84ba2257d67d810","abstract_canon_sha256":"50723897969f12aa3f9e486197867976258b92d94e2027f1db08286f50b67f1b"},"schema_version":"1.0"},"canonical_sha256":"ecc6cdef52d660b6b2de4e1eb0aca967af3e0813ad5b3a444c789c1eac0671b2","receipt":{"kind":"pith_receipt","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ecc6cdef52d660b6b2de4e1eb0aca967af3e0813ad5b3a444c789c1eac0671b2","last_reissued_at":"2026-07-30T01:21:58.355478Z","signature_status":"unsigned_v0","first_computed_at":"2026-07-30T01:21:58.355478Z"},"source_kind":"arxiv","source_id":"2607.26699","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-30T01:21:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2Asqf68AW5mRE26iDke/6wxeXF2e+HUXW/y6k+T2zcnPv6XM2YltafRa7ElrICqZto7bBXL86StqwBcodgXFBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T19:36:30.898996Z"},"content_sha256":"8f33101ad185c22113307453786db999a455c3a78c217c2bf3249372d29705a8","schema_version":"1.0","event_id":"sha256:8f33101ad185c22113307453786db999a455c3a78c217c2bf3249372d29705a8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:5TDM332S2ZQLNMW6JYPLBLFJM6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Universality and Approximation Rates of Graph Neural Networks with Random Features","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Lukas Gonon, Niklas Weber, Thilo Meyer-Brandis","submitted_at":"2026-07-29T09:46:07Z","abstract_excerpt":"We investigate message-passing graph neural networks with random node features. Random node features are known to enhance the expressiveness of graph neural networks (GNNs) both theoretically and empirically. Here, we establish a novel universality result focusing on permutation-equivariant neural networks (PENNs), a class of GNNs built from feedforward neural network components that subsumes many prominent GNN architectures. We show that PENNs, combined with partially random node features, can approximate arbitrarily well in probability any measurable permutation-invariant or permutation-equi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.26699","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2607.26699/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-30T01:21:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"b6g0MVU7W/AmEJS2DPzkPbXTewFSNRRwLdvFoAhmjXdRTghNM/1mQgByWsEbjP05+ldf4vpTo1w3DzKHnF7ZDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T19:36:30.899586Z"},"content_sha256":"767b49fb8b8b90aa9f4d4d3fb64e9e65b2a78e0cbd88493b53a7ab13c5ead051","schema_version":"1.0","event_id":"sha256:767b49fb8b8b90aa9f4d4d3fb64e9e65b2a78e0cbd88493b53a7ab13c5ead051"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5TDM332S2ZQLNMW6JYPLBLFJM6/bundle.json","state_url":"https://pith.science/pith/5TDM332S2ZQLNMW6JYPLBLFJM6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5TDM332S2ZQLNMW6JYPLBLFJM6/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-07T19:36:30Z","links":{"resolver":"https://pith.science/pith/5TDM332S2ZQLNMW6JYPLBLFJM6","bundle":"https://pith.science/pith/5TDM332S2ZQLNMW6JYPLBLFJM6/bundle.json","state":"https://pith.science/pith/5TDM332S2ZQLNMW6JYPLBLFJM6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5TDM332S2ZQLNMW6JYPLBLFJM6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:5TDM332S2ZQLNMW6JYPLBLFJM6","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"50723897969f12aa3f9e486197867976258b92d94e2027f1db08286f50b67f1b","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-29T09:46:07Z","title_canon_sha256":"c090934a95cff9c2cd1c1d74c16edcd3d4ca528aea45a701e84ba2257d67d810"},"schema_version":"1.0","source":{"id":"2607.26699","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.26699","created_at":"2026-07-30T01:21:58Z"},{"alias_kind":"arxiv_version","alias_value":"2607.26699v1","created_at":"2026-07-30T01:21:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.26699","created_at":"2026-07-30T01:21:58Z"},{"alias_kind":"pith_short_12","alias_value":"5TDM332S2ZQL","created_at":"2026-07-30T01:21:58Z"},{"alias_kind":"pith_short_16","alias_value":"5TDM332S2ZQLNMW6","created_at":"2026-07-30T01:21:58Z"},{"alias_kind":"pith_short_8","alias_value":"5TDM332S","created_at":"2026-07-30T01:21:58Z"}],"graph_snapshots":[{"event_id":"sha256:767b49fb8b8b90aa9f4d4d3fb64e9e65b2a78e0cbd88493b53a7ab13c5ead051","target":"graph","created_at":"2026-07-30T01:21:58Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2607.26699/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We investigate message-passing graph neural networks with random node features. Random node features are known to enhance the expressiveness of graph neural networks (GNNs) both theoretically and empirically. Here, we establish a novel universality result focusing on permutation-equivariant neural networks (PENNs), a class of GNNs built from feedforward neural network components that subsumes many prominent GNN architectures. We show that PENNs, combined with partially random node features, can approximate arbitrarily well in probability any measurable permutation-invariant or permutation-equi","authors_text":"Lukas Gonon, Niklas Weber, Thilo Meyer-Brandis","cross_cats":["stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-29T09:46:07Z","title":"Universality and Approximation Rates of Graph Neural Networks with Random Features"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.26699","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:8f33101ad185c22113307453786db999a455c3a78c217c2bf3249372d29705a8","target":"record","created_at":"2026-07-30T01:21:58Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"50723897969f12aa3f9e486197867976258b92d94e2027f1db08286f50b67f1b","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-29T09:46:07Z","title_canon_sha256":"c090934a95cff9c2cd1c1d74c16edcd3d4ca528aea45a701e84ba2257d67d810"},"schema_version":"1.0","source":{"id":"2607.26699","kind":"arxiv","version":1}},"canonical_sha256":"ecc6cdef52d660b6b2de4e1eb0aca967af3e0813ad5b3a444c789c1eac0671b2","receipt":{"builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ecc6cdef52d660b6b2de4e1eb0aca967af3e0813ad5b3a444c789c1eac0671b2","first_computed_at":"2026-07-30T01:21:58.355478Z","kind":"pith_receipt","last_reissued_at":"2026-07-30T01:21:58.355478Z","receipt_version":"0.3","signature_status":"unsigned_v0"},"source_id":"2607.26699","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8f33101ad185c22113307453786db999a455c3a78c217c2bf3249372d29705a8","sha256:767b49fb8b8b90aa9f4d4d3fb64e9e65b2a78e0cbd88493b53a7ab13c5ead051"],"state_sha256":"5d617e3159e68b9ba443a3be7071ddc3e246abe863b4fee0aa9d43c12e03cceb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bsP61jnlS0qk3Pfot1vR0+x2qzmCBl7/5QUybff7EQxdMag7GdFT+5/wEi9+UUH3mL9N18AalTpiJuNtaZWYCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T19:36:30.903660Z","bundle_sha256":"bced26cfd7e9c1607543ca9a7319326d7d5c0b61b0622c9b4185d4ca451e320e"}}